Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.4605. Min Act: -0.1700
Data Index: 6910138 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.1480. Min Act: -0.1700
Data Index: 7342194 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.1480. Min Act: -0.1700
Data Index: 5095390 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.1480. Min Act: -0.1699
Data Index: 8024093 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.1480. Min Act: -0.1696
Data Index: 5549165 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1679
Data Index: 3114995 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 1245764 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 8181368 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1698
Data Index: 590537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 8798698 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1699
Data Index: 3980675 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 1671426 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 4391688 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 2003932 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 791678 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1694
Data Index: 6761265 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 260726 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 3378901 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 1397715 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4605. Min Range: -8.4605
Max Act: 8.0230. Min Act: -0.1699
Data Index: 7146246 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19